以自适应回波对消为对象，讨论了两种自适应符号算法的梯度估计平滑方法。
Two smoothed gradient estimate methods used in adaptive sign algorithm applied to adaptive echo canceling have been discussed in this paper.
然后利用这种模式的特点，在线优化算法相结合的策略梯度估计及随机逼近而得。
Then by utilizing the features of this model an online optimization algorithm that combines policy gradient estimation and stochastic approximation is derived.
均值漂移算法是一种基于核密度梯度估计的特征空间分析算法，其实质是一种统计优化过程。
Mean shift based image segmentation algorithm is a kind of kernel density estimation based feature space analysis algorithm, and the nature of it is statistical optimization.
基于信号在不同尺度下小波变换系数模不同的变化特征，结合最优梯度估计算法提出了一种边缘检测方法。
Based on different properties of the coefficient modulus of the signal in different scale wavelet transform, conjunction the best estimate of gradient algorithm an edge detecting method is proposed.
本文分析了梯度辨识算法跟踪时变系统的缺点，提出了一种新的基于局部多项式逼近的变参数梯度估计算法。
The trackability limitation of current gradient algorithm is discussed. A new algorithm, named variable parameter gradient estimation algorithm with local polynomial approximation is proposed.
首先提出了局部图像的梯度估计方法，称之为BEG(梯度的最佳估计)算法，用来提取图像的纹理方向特征参数。
First, a method to estimate the local image gradient, called the BEG (best estimation of gradient) algorithm was proposed to extract the texture orientation parameters.
当相位梯度算法挑选的散射点不是孤立散射点时，导致相位误差估计的准确性下降。
If the scatter selected in phase gradient algorithm(PGA) algorithm is not isolated, the accuracy of the phase error estimation will be degraded.
在实际应用中，不同类型地震噪声的存在给截距和梯度的可靠估计带来了很大困难。
In practice, the existence of different types of seismic noises causes significant difficulties to reliably estimate intercept and gradient.
计算结果表明，这种新方法不但能估计压力梯度，而且还能给出浆体速度分布。
The computed result shows that this new method can not only predict the pressure gradient but can also give the velocity profile.
第一章是绪论部分。简要介绍了投影梯度方法，误差界估计以及本文的主要工作。
Chapter 1 is the introduction of this paper, which introduces the the projected gradient method, the error bounds estimation and the main results obtained in this paper.
第三章研究了投影梯度方法的误差界估计。
In Chapter 3, some error bounds estimations of the projected gradient methods are obtained.
本文采用了基于梯度法的运动估计，因为它能很好地对大位移的图像进行精确的配准。
This thesis adopts a gradient image registration method which is based on the Taylor theory. Since it can provide a good registration for big shifted image.
首先改进传统的一维梯度下降搜索算法，并提出由梯度下降方向自适应选择不同的抽取模式去除计算运动估计准则时的冗余。
This method proposes five decimation patterns based on the gradient descent direction, and it can select the decimation pattern adaptively during the motion estimation.
将鲁棒估计方法与多尺度方法相结合，给出了一种基于梯度的鲁棒分层估计多尺度运动估计算法。
A robust multiscale algorithm of hierarchical estimation for gradient-based motion estimation was proposed, by a combination of robust estimation method and multiscale technique.
它对一定时间间隔内两次采样得到的图象进行运算，用最陡梯度下降法直接迭代出图象位移的估计值。
The algorithm which utilizes the Steepest Descent Method can give the estimation of displacement between two frames of image directly.
另外，针对进行相似性变换的目标也提出了一种新的候选目标模型，并用类似的梯度下降算法估计目标的平移向量和旋转角度。
Furthermore, a new candidate model is proposed that handles similarity transformation, and the corresponding MS algorithm can be obtained that estimates the translation vector and rotation Angle.
将鲁棒估计方法与多尺度方法相结合，给出了一种基于梯度的鲁棒分层估计多尺度运动估计算法。
This article, based on the hierarchical motion estimation (HME), proposes a new side information generation algorithm which is integrated into DVC system.
最后采用基于迭代的方法，重新估计所有块梯度向量并将梯度向量场转化为方向场。
This new method mainly comprises three steps: firstly, normalize the point-gradient vectors and calculate the block-gradient vectors and the corresponding block-coherence;
最后采用基于迭代的方法，重新估计所有块梯度向量并将梯度向量场转化为方向场。
This new method mainly comprises three steps: firstly, normalize the point-gradient vectors and calculate the block-gradient vectors and the corresponding block-coherence;
应用推荐